Zero-shot Composed Text-Image Retrieval

12 Jun 2023  Β·  Yikun Liu, Jiangchao Yao, Ya zhang, Yanfeng Wang, Weidi Xie Β·

In this paper, we consider the problem of composed image retrieval (CIR), it aims to train a model that can fuse multi-modal information, e.g., text and images, to accurately retrieve images that match the query, extending the user's expression ability. We make the following contributions: (i) we initiate a scalable pipeline to automatically construct datasets for training CIR model, by simply exploiting a large-scale dataset of image-text pairs, e.g., a subset of LAION-5B; (ii) we introduce a transformer-based adaptive aggregation model, TransAgg, which employs a simple yet efficient fusion mechanism, to adaptively combine information from diverse modalities; (iii) we conduct extensive ablation studies to investigate the usefulness of our proposed data construction procedure, and the effectiveness of core components in TransAgg; (iv) when evaluating on the publicly available benckmarks under the zero-shot scenario, i.e., training on the automatically constructed datasets, then directly conduct inference on target downstream datasets, e.g., CIRR and FashionIQ, our proposed approach either performs on par with or significantly outperforms the existing state-of-the-art (SOTA) models. Project page:

PDF Abstract


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Zero-Shot Composed Image Retrieval (ZS-CIR) CIRR TransAgg(Laion-CIR-Combined) R@5 68.88 # 1
Zero-Shot Composed Image Retrieval (ZS-CIR) Fashion IQ TransAgg (Laion-CIR-Combined) (Recall@10+Recall@50)/2 44.75 # 4


No methods listed for this paper. Add relevant methods here